Nonlinear Regularization Decoding Method for Speech Recognition.

Existing end-to-end speech recognition methods typically employ hybrid decoders based on CTC and Transformer. However, the issue of error accumulation in these hybrid decoders hinders further improvements in accuracy. Additionally, most existing models are built upon Transformer architecture, which tends to be complex and unfriendly to small datasets. Hence, we propose a Nonlinear Regularization Decoding Method for Speech Recognition. Firstly, we introduce the nonlinear Transformer decoder, breaking away from traditional left-to-right or right-to-left decoding orders and enabling associations between any characters, mitigating the limitations of Transformer architectures on small datasets. Secondly, we propose a novel regularization attention module to optimize the attention score matrix, reducing the impact of early errors on later outputs. Finally, we introduce the tiny model to address the challenge of overly large model parameters. The experimental results indicate that our model demonstrates good performance. Compared to the baseline, our model achieves recognition improvements of 0.12%, 0.54%, 0.51%, and 1.2% on the Aishell1, Primewords, Free ST Chinese Corpus, and Common Voice 16.1 datasets of Uyghur, respectively.

Echo-Enhanced Embodied Visual Navigation.

Visual navigation involves a movable robotic agent striving to reach a point goal (target location) using vision sensory input. While navigation with ideal visibility has seen plenty of success, it becomes challenging in suboptimal visual conditions like poor illumination, where traditional approaches suffer from severe performance degradation. We propose E3VN (echo-enhanced embodied visual navigation) to effectively perceive the surroundings even under poor visibility to mitigate this problem. This is made possible by adopting an echoer that actively perceives the environment via auditory signals. E3VN models the robot agent as playing a cooperative Markov game with that echoer. The action policies of robot and echoer are jointly optimized to maximize the reward in a two-stream actor-critic architecture. During optimization, the reward is also adaptively decomposed into the robot and echoer parts. Our experiments and ablation studies show that E3VN is consistently effective and robust in point goal navigation tasks, especially under nonideal visibility.

Edge-Guided Camouflaged Object Detection via Multi-Level Feature Integration.

Camouflaged object detection (COD) aims to segment those camouflaged objects that blend perfectly into their surroundings. Due to the low boundary contrast between camouflaged objects and their surroundings, their detection poses a significant challenge. Despite the numerous excellent camouflaged object detection methods developed in recent years, issues such as boundary refinement and multi-level feature extraction and fusion still need further exploration. In this paper, we propose a novel multi-level feature integration network (MFNet) for camouflaged object detection. Firstly, we design an edge guidance module (EGM) to improve the COD performance by providing additional boundary semantic information by combining high-level semantic information and low-level spatial details to model the edges of camouflaged objects. Additionally, we propose a multi-level feature integration module (MFIM), which leverages the fine local information of low-level features and the rich global information of high-level features in adjacent three-level features to provide a supplementary feature representation for the current-level features, effectively integrating the full context semantic information. Finally, we propose a context aggregation refinement module (CARM) to efficiently aggregate and refine the cross-level features to obtain clear prediction maps. Our extensive experiments on three benchmark datasets show that the MFNet model is an effective COD model and outperforms other state-of-the-art models in all four evaluation metrics (Sα, Eϕ, Fßw, and MAE).

Study on the Preparation and Optical Properties of Graphene Oxide@Fe3O4 Two-Dimensional Magnetically Oriented Nanocomposites.

In this work, graphene oxide@Fe3O4 (GO@Fe3O4) two-dimensional magnetically oriented nanocomposites were prepared through the co-precipitation approach using graphene oxide as the carrier and FeCl3·6H2O and FeSO4·7H2O as iron sources. The samples were characterized and tested by X-ray diffraction, a transmission electron microscope, Fourier-transform infrared spectroscopy, a vibrating-specimen magnetometer, a polarized optical microscope, an optical microscope, etc. The effects of material ratios and reaction conditions on the coating effects of Fe3O4 on the GO surface were investigated. The stable GO@Fe3O4 sol system was studied and constructed, and the optical properties of the GO@Fe3O4 sol were revealed. The results demonstrated the GO@Fe3O4 two-dimensional nanocomposites uniformly coated with Fe3O4 nanoparticles were successfully prepared. The GO@Fe3O4 two-dimensional nanocomposites exhibited superparamagnetic properties at room temperature, whose coercive force was 0. The stable GO@Fe3O4 sol system could be obtained by maintaining 1 < pH < 1.5. The GO@Fe3O4 sol showed magneto-orientation properties, liquid crystalline properties, and photonic crystal properties under the influence of the external magnetic field. The strength and direction of the magnetic field and the solid content of the GO@ Fe3O4 sol could regulate the aforementioned properties. The results suggest that GO@Fe3O4 two-dimensional magnetically oriented nanocomposites have potential applications in photonic switches, gas barriers, and display devices.